A Transformation-Based Improved Kriging Method for the Black Box Problem in Reliability-Based Design Optimization

In order to overcome the drawbacks of expensive function evaluation in practical reliability-based design optimization (RBDO) problem, researchers have proposed black box-based RBDO method. The algorithm flow commonly employed method for box problem consists outer construction loop surrogate model constraint and inner model-based solving loop. To improve ability this paper proposes a transformation-based improved kriging increase effectiveness two loops identified above. For loop, sample distribution-based learning is suggested efficiency function. paired incremental sample-based limit reliability boundary approach transform into an equivalent deterministic that can be efficiently solved by classical algorithms. test results five cases demonstrate accurately construct solve problem.